In: Statistics and Probability
Here is a data set:
4580 4270 1970 5610 3000 3540 4420 2770 1970 3850 3730 2600 3980 4140 2690 4110 6350 3450 4990 4560 3290 2590 2560 3010 2510 5750 2710 5170
Construct a grouped frequency distribution table (GFDT) for this data set. You want 10 classes with a "nice" class width. Your classes should be labeled using interval notation. Each class contains its lower class limit, and the lower class limits should all be multiples of the class width. In that the data appears to be discrete, use a closed-interval to label each class.
Given data set,
4580 4270 1970 5610 3000 3540 4420 2770 1970 3850 3730 2600 3980 4140 2690 4110 6350 3450 4990 4560 3290 2590 2560 3010 2510 5750 2710 5170
Now we construct a grouped frequency distribution table (GFDT) for this data set with 10 classes and lower class limits of each class should be multiples of the class width. And we use closed-interval to label each class.
Here we see that the maximum value of the data set is 6350 and minimum value of the data set is 1970.
So, WLG we take 1840 as a lower class limit of 1st class and take class width as 460.
So our 10 classes is given by,
1840-2300, 2300-2760, 2760-3220, 3220-3680, 3680-4140, 4140-4600, 4600-5060, 5060-5520, 5520-5980, 5980-6440.
[ Note:- All lower class limits are excluding and all the upper class limits are including. That means the data 4140 included in 5th class (3680-4140) not in 6th class (4140-4600) ]
Grouped Frequency Distribution Table:-
[ Note:- Here if data lies in between class then class get a tally mark. And total number of tally mark of class is the frequency of class. And relative frequency of a class given by the formula,
Relative frequency = (Frequency of that class / Total frequency) ]